PMMLPredict Syntax Elements | Vantage BYOM - 3.0 - PMMLPredict Syntax Elements - Teradata Vantage

Teradata Vantageā„¢ - Bring Your Own Model User Guide

Teradata Vantage
Release Number
Release Date
May 2022
Content Type
User Guide
Publication ID
English (United States)
[Optional] Specify the schema in which PMMLPredict is installed.
Default: mldb
Specify one or more InputTable columns to copy to the output table. The asterisk specifies all InputTable columns.
An accumulate_column cannot have the reserved column name 'prediction' or 'json_report' or the data type BLOB or CLOB.
You cannot specify the same accumulate_column more than once.
[Optional] Specify the scoring fields to output as individual columns (instead of outputting the JSON string that contains all the scoring output fields). For information about PMML output fields, see
To specify a model_output_field that is not in the JSON string is an error.
Default behavior: The function outputs the JSON string that contains all the output fields in the output table column json_report.
[Optional] Valid values are: 'current_cached_model', '*', 'true', 't', 'yes', '1', 'false', 'f', 'no', 'n', or '0'. All of these values are equivalent as this argument applies only to the model specified in the model ON clause, which is assumed to be in the cache.
Important: Do not use the OverwriteCachedModel argument except when you are trying to replace a previously cached model. This applies to any model type (PMML, H2O Open Source, DAI, and ONNX). Using the argument in other cases, including in concurrent queries or multiple times within a short period of time, may lead to an OOM error from garbage collection not being fast enough.
If a model loaded into the memory of the node fits in the cache, it stays in the cache until being evicted to make space for another model that needs to be loaded. Therefore, a model can remain in the cache after the query that loaded it completes. Other queries that use the same model can use it, saving the cost of reloading it into memory.
You want to overwrite a cached model only when it has been updated, to make sure that the Predict function uses the updated model instead of the cached model.
Default behavior: The function does not overwrite cached models.